Two-Sample t-Test Assuming Equal Variances in Excel
You can do a t-Test in Excel using the Analysis Toolpak, but...
- Excel won't interpret your p-value for you; the QI Macros will!
- Excel can't give you a Box and Whisker chart of the two factors; the QI Macros can!
How do you determine if the variances are equal or unequal? Use an F-test to determine if the variances are equal or unequal.
If they are not equal go to: Two-Sample t-Test assuming unequal variances.
(The QI Macros Stat Wizard will do this for you automatically.)
t-Test Two-Sample Assuming Equal Variances Video
t-Test Two-Sample Assuming Equal Variances Example
If you're producing rubber made from two different recipes, you might want to know if the tensile strengths are the same or different. So you test five samples of each to get the data:
Warning: While you can run a t-Test using Excel's Data Analysis Toolpak, if you don't enter the two columns in the correct order, Excel will give you incorrect results. The QI Macros have eliminated this problem.
To conduct an t-test using the QI Macros for Excel, follow these steps:
- Select the data with your mouse and click on the QI Macros Menu and select the Statistical Tools->Two-Sample t-Test Assuming Equal Variances:
- The QI Macros will prompt for a significance level (default is .05, or use 0.01 or 0.001):
Note: Significance Level = (1 - Confidence Level)
- Next the QI Macros will prompt for the hypothesized difference in the means (default is 0).
If you specify a mean difference other than zero, use:
- two-tail p value (Difference = Hypothesized Mean Difference)
- one-tail p value (Difference < Hypothesized Mean Difference)
- 1-one tail p value (Difference > Hypothesized Mean Difference)
- The QI Macros will perform the calculations and interpret the results for you:
Interpreting t-Test Results With QI Macros
Note: Native Excel will not interpret the test results for you, but the QI Macros will compare the p-value (0.818) to the significance level (0.05) and tell you "Cannot Reject the Null Hypothesis because p>0.05" and that the "Means are the same."
Confidence limits indicate how much uncertainty there is in the difference between the two means. A narrower interval means a more precise estimate.
- How to interpret Excel t-test results
- Equivalence Test
- Two-Sample t-Test assuming unequal variances
- t-Test one sample
- Paired Two-Sample t-Test
- Statistics Wizard analyzes your data and selects the right statistical tests for you